Perhaps, the greatest discovery of the year is here. Good news for all the photo freaks out there who can cross miles, just for that single perfect image. So, in view to this, Google, in collaboration with the scientists at MIT, have invented computational photography. In clear terms, this latest research uses algorithms and machine learning that are able to edit or filter the photos like a pro, even before clicking them. Thus taking photography to a completely different new level.
The researchers started this unique process by resorting to machine learning to create their own software, training neural networks on a dataset of 5,000 images created by Adobe and MIT. 5 different photographers have worked on each of these images, and the algorithms by Google and MIT have taken a note of this data to decipher the kind of improvements used to make the different photos. This mainly referred to increasing the brightness of one image while reducing the saturation of another one.
Now, this new method of filtering or enhancing the images can be found similar to that of the artistic filters that mimicked the famous painters, founded upon by Facebook and Prisma. Also, the undeniable fact remains that the smartphones and cameras have already initiated the process imaging data in real time, but of course these new techniques are much more subtle and reactive, catering directly to the individual of the images instead of applying the general rules.
Also, to lessen down the methods, the researchers have found new techniques. These enlist turning the changes made to each photo into formulae and using the grid- like coordinates to map the picture. This implies that the steps to retouch the photos can be explained in mathematical steps instead of full-scale photos.
Lastly, Google researcher and MIT Professor Jon Barron regarded that, “This technology has the potential to be very useful for real-time image enhancement on mobile platforms.Using machine learning for computational photography is an exciting prospect but is limited by the severe computational and power constraints of mobile phones. This paper may provide us with a way to sidestep these issues and produce new, compelling, real-time photographic experiences without draining your battery or giving you a laggy viewfinder experience”.